{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:35V4GGIETIYOSVYAZZ66Q6EJGU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c5d7d281c17a07303f5fbde08300d1ea36929b59bbe73cdae5c5ada817999916","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T12:11:49Z","title_canon_sha256":"9d073a63ef6db40ea79882a490dfb2f4981e9c5ceaa585576f10acc0254d4e75"},"schema_version":"1.0","source":{"id":"2607.02073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02073","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02073v1","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02073","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"35V4GGIETIYO","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"35V4GGIETIYOSVYA","created_at":"2026-07-03T01:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"35V4GGIE","created_at":"2026-07-03T01:17:38Z"}],"graph_snapshots":[{"event_id":"sha256:29d670987228e96f644ff3073ef9d6a25553da3341546ecc002526ebe446664a","target":"graph","created_at":"2026-07-03T01:17:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.02073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-context reasoning requires models to locate, revise, and synthesize evidence distributed across lengthy inputs. Existing long-context RL methods usually reward final answers or static evidence extraction, offering little feedback on how intermediate actions change the model's evidence state. We propose Maven, a reinforcement learning framework with an editable evidence memory. Maven defines an answer-conditioned evidence-state value and rewards action-level state transitions: add actions are credited by marginal gain and hindsight contribution, link actions by evidence synergy, and drop a","authors_text":"Pekka Marttinen, Ya Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T12:11:49Z","title":"Evidence-State Rewards for Long-Context Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02073","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5e2991e13399577419007a6ca938afbe35d37ec46c46f46e628e0cb93d7c40ca","target":"record","created_at":"2026-07-03T01:17:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c5d7d281c17a07303f5fbde08300d1ea36929b59bbe73cdae5c5ada817999916","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T12:11:49Z","title_canon_sha256":"9d073a63ef6db40ea79882a490dfb2f4981e9c5ceaa585576f10acc0254d4e75"},"schema_version":"1.0","source":{"id":"2607.02073","kind":"arxiv","version":1}},"canonical_sha256":"df6bc319049a30e95700ce7de878893521ddd1a2f4dc1a0e4d86ca5eb81626d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df6bc319049a30e95700ce7de878893521ddd1a2f4dc1a0e4d86ca5eb81626d6","first_computed_at":"2026-07-03T01:17:38.994518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:38.994518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uz79+6iH4WYcIUOxYv1326fWu1378TeXKFk5ur476vKVf9u8IeOyb2WxkueKeXBqKYTI+RAM/XzxpifUP5m8Dg==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:38.994933Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e2991e13399577419007a6ca938afbe35d37ec46c46f46e628e0cb93d7c40ca","sha256:29d670987228e96f644ff3073ef9d6a25553da3341546ecc002526ebe446664a"],"state_sha256":"e5abb5e0ce8d1844956bcc25688366d3d3929e90e6080314229f8f2393e62f4a"}